[Elenco soci]

Pubblicazioni scientifiche

[1] Sanseverino G., Krumm D., Kopnarski L., Rudisch J., Voelcker-Rehage C., Odenwald S., Preliminary Validation of a Virtual Environment for Simulation and Recognition of Human Gestures, Lecture Notes in Mechanical Engineering, 605-613, (2023). Abstract

Abstract: Humans are able to communicate by a wide variety of means. Gestures often play an important role in this multimodal communication. In order to also ensure robust interaction between humans and machines, it is important that machines are able to recognize human gestures. This typically requires time-consuming subject tests that limit the number of conditions that can be tested. However, by moving these tests from the physical to a virtual environment, each test condition can be evaluated quickly, eliminating the need for numerous repetitions. The purpose of this work was to validate the use of a virtual test environment in comparison to physical testing. This was done by conducting a subject test and developing a virtual model of the human upper limb. The motion profile of the subject performing a simple gesture was recorded with a visual optical motion capture system and used as input for the newly developed virtual model. Acceleration signals captured with an IMU attached to the subject's right wrist were used as a reference signal and compared to signals simulated by a digital twin of the sensor. The pilot study proved the capabilities of the proposed approach and showed some of its limitations.

Keywords: Digital twin | Human body model | Human gestures | Simulation | Virtual environment

[2] Caporaso T., Sanseverino G., Krumm D., Grazioso S., D’Angelo R., Di Gironimo G., Odenwald S., Lanzotti A., Automatic Outcomes in Minnesota Dexterity Test Using a System of Multiple Depth Cameras, Lecture Notes in Mechanical Engineering, 286-293, (2023). Abstract

Abstract: Objective and reliable assessment of motor functions, such as dexterity, is a key point for evaluating worker’s abilities. In this context, the proposed work presents a tool for objective automatic assessment of the Minnesota Dexterity Test using cameras with depth sensors. Typical performance measurements (i.e., total time and associated percentiles) were estimated using custom algorithms. In addition, the possibility to identify the qualifiers for the code d440 of the International Classification of Functioning, Disability and Health was implemented in the developed algorithms. The proposed tool can also identify the mistakes most frequently committed by the subjects. To prove the capabilities of the proposed method, a series of experimental trials was conducted with 10 healthy young volunteers. Results showed that the developed tool helps clinicians to obtain performance feedback and evaluate patients’ dexterity quickly without bias.

Keywords: Automatic assessment | Biomechanics | Depth cameras | Manual dexterity | Motion capture

[3] Sanseverino G., Krumm D., Odenwald S., A Framework for Virtual Evaluation of Body-Attached Sensor Networks, Lecture Notes in Mechanical Engineering, 557-568, (2022). Abstract

Abstract: In this work, we propose a framework that can be used for virtual evaluation of Body-Attached Sensor Networks. Normally, the evaluation of Body-Attached Sensor Networks requires numerous subject tests under laboratory conditions. However, since it is difficult to perform the same motion repeatedly without minute deviations, numerous replicate measurements are required to obtain statistically meaningful measurements. To overcome this limitation, we propose the use of virtual environments. These provide both a high degree of flexibility, since a movement can be repeated in the same way each time, and the ability to test many different sensor setups quickly and with little effort. To this end, we modeled the human body parts of interest using the MATLAB tool Simscape Multibody. Digital twins were then implemented in this model to represent real sensors along with their sensor properties at arbitrary locations. This makes it possible to check many different sensor types and their position on the body in a short time without having to perform subject tests. This framework creates a solid basis for the development of effective Body-Attached Sensor Networks.

Keywords: Digital twins | Multibody simulation | Sensor networks | Virtual environment | Wearable

[4] Ramalingame R., Barioul R., Li X., Sanseverino G., Krumm D., Odenwald S., Kanoun O., Wearable Smart Band for American Sign Language Recognition with Polymer Carbon Nanocomposite-Based Pressure Sensors, IEEE Sensors Letters, 5(6), (2021). Abstract

Abstract: The conventional camera-based systems and electronic gloves for gesture recognition are limited by the influence of lighting conditions, occlusions, and movement restrictions. A wearable smart band with integrated nanocomposite pressure sensors has been developed to overcome these shortcomings. The sensors consist of homogeneously dispersed carbon nanotubes in a polydimethylsiloxane polymer matrix prepared by an optimized synthesis process. The sensor band can actively monitor contractions/relaxations of muscles in the arm due to the sensor's high sensitivity in the low forces and stability. The band has eight sensors placed on a stretchable adhesive textile material and connected to a data logger with a multiplexed sensor interface and wireless communication capabilities. The novel smart band was validated by measurements on ten subjects to perform numerical gestures in American sign language from 0 to 9 with ten trials each. The data were recorded at 100 Hz, and a total of 100 datasets were generated for each subject. By feeding the datasets to an extreme machine learning algorithm that selects features, weights, and biases to classify the gestures, an overall gesture recognition accuracy of 93% could be achieved.

Keywords: American sign language | gesture recognition | polymer carbon nanocomposite (PCN) pressure sensors | Sensor applications | wearable smart band

[5] Sanseverino G., Schwanitz S., Krumm D., Odenwald S., Lanzotti A., Towards innovative road cycle gloves for low vibration transmission, International Journal on Interactive Design and Manufacturing, 15(1), 155-158, (2021). Abstract

Abstract: This research activity aims to develop new cycling gloves. A first step was focused on the definition of the functional requirements through user centred design methods. Since vibrations coming to the hand-arm system of a cyclist have a considerable effect a second step was concentrated on the analysis of hand-arm vibrations in road cycling. The paper shows results of laboratory tests executed for three different hand sizes, three different frequency ranges, with two different type of gloves and without gloves. Load conditions used for the test were determined with a former field test. Results obtained were analysed using Analysis of Variance (ANOVA), that showed no significant effect of existing gloves in reducing vibration transmissibility. This led to the need of new kind of cycling gloves that could reduce those vibrations and increase the cyclist’s comfort.

Keywords: Bioengineering | Cycling gloves | Design of experiments | Road cycling | Sport equipment | User centred design | Vibration transmission